diff options
| -rw-r--r-- | clang/include/clang/Driver/Options.td | 4 | ||||
| -rw-r--r-- | clang/lib/Driver/ToolChains/Cuda.cpp | 5 | ||||
| -rw-r--r-- | clang/test/Driver/openmp-offload.c | 17 |
3 files changed, 25 insertions, 1 deletions
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td index d866c16dbb6..c86941181b7 100644 --- a/clang/include/clang/Driver/Options.td +++ b/clang/include/clang/Driver/Options.td @@ -1311,6 +1311,10 @@ def fopenmp_targets_EQ : CommaJoined<["-"], "fopenmp-targets=">, Flags<[DriverOp HelpText<"Specify comma-separated list of triples OpenMP offloading targets to be supported">; def fopenmp_dump_offload_linker_script : Flag<["-"], "fopenmp-dump-offload-linker-script">, Group<f_Group>, Flags<[NoArgumentUnused]>; +def fopenmp_relocatable_target : Flag<["-"], "fopenmp-relocatable-target">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>, + HelpText<"OpenMP target code is compiled as relocatable using the -c flag. For OpenMP targets the code is relocatable by default.">; +def fnoopenmp_relocatable_target : Flag<["-"], "fnoopenmp-relocatable-target">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>, + HelpText<"Do not compile OpenMP target code as relocatable.">; def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>; def foptimize_sibling_calls : Flag<["-"], "foptimize-sibling-calls">, Group<f_Group>; def force__cpusubtype__ALL : Flag<["-"], "force_cpusubtype_ALL">; diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp index 927704a6857..1ff41ce66d4 100644 --- a/clang/lib/Driver/ToolChains/Cuda.cpp +++ b/clang/lib/Driver/ToolChains/Cuda.cpp @@ -292,7 +292,10 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA, CmdArgs.push_back(Args.MakeArgString(A)); // In OpenMP we need to generate relocatable code. - if (JA.isOffloading(Action::OFK_OpenMP)) + if (JA.isOffloading(Action::OFK_OpenMP) && + Args.hasFlag(options::OPT_fopenmp_relocatable_target, + options::OPT_fnoopenmp_relocatable_target, + /*Default=*/ true)) CmdArgs.push_back("-c"); const char *Exec; diff --git a/clang/test/Driver/openmp-offload.c b/clang/test/Driver/openmp-offload.c index af50d156d7d..cd2ca3e3d6e 100644 --- a/clang/test/Driver/openmp-offload.c +++ b/clang/test/Driver/openmp-offload.c @@ -695,3 +695,20 @@ // RUN: | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s // CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c" + +/// ########################################################################### + +/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP - disable it. +// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \ +// RUN: | FileCheck -check-prefix=CHK-PTXAS-NORELO %s + +// CHK-PTXAS-NORELO-NOT: ptxas{{.*}}" "-c" + +/// ########################################################################### + +/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP +/// Check that the flag is passed when -fopenmp-relocatable-target is used. +// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \ +// RUN: | FileCheck -check-prefix=CHK-PTXAS-RELO %s + +// CHK-PTXAS-RELO: ptxas{{.*}}" "-c" |

